Differentially Private Wasserstein Barycenters
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912626305400832 |
|---|---|
| author | Gu, Anming Kunapuli, Sasidhar Bun, Mark Chien, Edward Greenewald, Kristjan |
| author_facet | Gu, Anming Kunapuli, Sasidhar Bun, Mark Chien, Edward Greenewald, Kristjan |
| contents | The Wasserstein barycenter is defined as the mean of a set of probability measures under the optimal transport metric, and has numerous applications spanning machine learning, statistics, and computer graphics. In practice these input measures are empirical distributions built from sensitive datasets, motivating a differentially private (DP) treatment. We present, to our knowledge, the first algorithms for computing Wasserstein barycenters under differential privacy. Empirically, on synthetic data, MNIST, and large-scale U.S. population datasets, our methods produce high-quality private barycenters with strong accuracy-privacy tradeoffs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03021 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Differentially Private Wasserstein Barycenters Gu, Anming Kunapuli, Sasidhar Bun, Mark Chien, Edward Greenewald, Kristjan Machine Learning The Wasserstein barycenter is defined as the mean of a set of probability measures under the optimal transport metric, and has numerous applications spanning machine learning, statistics, and computer graphics. In practice these input measures are empirical distributions built from sensitive datasets, motivating a differentially private (DP) treatment. We present, to our knowledge, the first algorithms for computing Wasserstein barycenters under differential privacy. Empirically, on synthetic data, MNIST, and large-scale U.S. population datasets, our methods produce high-quality private barycenters with strong accuracy-privacy tradeoffs. |
| title | Differentially Private Wasserstein Barycenters |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.03021 |